INDEX

Explanations

references to "face" and "confrontation."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nearby

-0.49

Nearby

-0.42

nearby

-0.41

 Füßen

-0.41

 contextLoads

-0.40

 neighbouring

-0.40

 Nearby

-0.39

 Ausrüstung

-0.39

 estekak

-0.38

}{*}{}

-0.38

POSITIVE LOGITS

 face

0.74

 Face

0.69

 оригіналу

0.66

HasAnnotation

0.65

Face

0.65

PYX

0.65

 confront

0.63

face

0.63

faced

0.63

Fac

0.58

Activations Density 1.625%

references to "face" and "confrontation."

No Comments

No Known Activations